Ratna Babu Chinnam

Data-driven battery prognostics can fail when models trained on one chemistry are deployed on another. This study investigates early-life end-of-life (EOL) classification under chemistry-driven domain shift and introduces a schema-constrained large language model (LLM) configuration layer as the primary methodological contribution. The LLM does not predict EOL directly and does not introduce a new transfer-learning or uncertainty-estimation algorithm. Instead, it maps structured chemistry context and numerical dataset evidence to an executable architecture, reliability head, and bounded set of training hyperparameters selected from an approved model zoo containing one-dimensional CNN, self-attention, WideResNet, OpenMax, and Spectral-normalized Neural Gaussian Process (SNGP) options. Full degradation trajectories define five EOL categories using an 80% state-of-health threshold, whereas model inputs are restricted to early-cycle observations. Across six directed Argonne/CAMP chemistry-transfer tasks, the target-only deterministic CNN achieved a mean balanced accuracy of 68.9%, compared with 78.3% for the LLM-selected CNN with self-attention and SNGP, corresponding to an average improvement of 9.4 percentage points. Fixed non-LLM transfer alternatives achieved 70.0% for the deterministic CNN, 71.7% for the OpenMax-enforced CNN, 66.5% for deterministic WideResNet, and 73.3% for WideResNet-SNGP. Context ablation further reduced LLM-selected accuracy from 78.3% with history and chemistry context to 73.5% without history, 71.6% without chemistry, and 67.1% when both were removed. These results support the use of constrained LLM guidance as an auditable configuration-selection layer, while cross-chemistry transfer learning and uncertainty-aware EOL prediction provide the experimental setting in which that selection mechanism is evaluated.

Data-driven battery prognostics can fail when models trained on one chemistry are de-ployed on another. This study proposes a constrained large language model (LLM)-guided model-selection framework for early-life end-of-life (EOL) classification under chemistry-driven domain shift. Full degradation trajectories define five EOL categories using an 80% state-of-health threshold, whereas model inputs are restricted to early-cycle windows. Structured chemistry context and numerical dataset summaries guide selection from a bounded model zoo comprising one-dimensional CNN, self-attention, WideResNet, OpenMax, and Spectral-normalized Neural Gaussian Process (SNGP) options; outputs are schema-validated and logged. The framework is evaluated on Argonne/CAMP cycling data across NMC, Li-rich, 5V spinel, and FCG cathode-family transfer tasks. The LLM-selected CNN with self-attention and SNGP achieved an average improvement of 9.4 percentage points over the target-only deterministic CNN baseline, compared with 2.8 percentage points for the deterministic CNN transfer model and 4.4 percentage points for WideResNet-SNGP. Cross-domain comparison with prior CWRU bearing results suggests that uncertainty-aware heads are useful across diagnostic and prognostic tasks, whereas OpenMax is most relevant when label support is explicitly open-set. These results position constrained LLM guidance as an auditable configuration layer rather than an unconstrained optimizer.

Intelligent Fault Diagnosis (IFD) systems are integral to predictive maintenance and real-time monitoring but often encounter challenges such as data scarcity, non-linearity, and changing operational conditions. To address these challenges, we propose an enhanced transfer learning framework that integrates the Universal Adaptation Network (UAN) with Spectral-normalized Neural Gaussian Process (SNGP), WideResNet, and attention mechanisms, including self-attention and an outlier attention layer. UAN’s flexibility bridges diverse fault conditions, while SNGP’s robustness enables uncertainty quantification for more reliable diagnostics. WideResNet’s architectural depth captures complex fault patterns, and the attention mechanisms focus the diagnostic process. Additionally, we employ Optuna for hyperparameter optimization, using a structured study to fine-tune model parameters and ensure optimal performance. The proposed approach is evaluated on benchmark datasets, demonstrating superior fault identification accuracy, adaptability to varying operational conditions, and resilience against data anomalies compared to existing models. Our findings highlight the potential of advanced machine learning techniques in IFD, setting a new standard for applying these methods in complex diagnostic environments.

Monitoring and prognostics of energy assets are crucial for maintaining their reliability and efficiency. Effective monitoring ensures that potential issues are identified early, preventing unexpected failures and optimizing maintenance schedules. However, several challenges complicate this process in real-world scenarios, including poor data quality, low-fidelity and sparse data, the influence of external environmental factors, and diverse operating conditions and asset types. These challenges highlight the need for adaptable and generic solutions that can handle variability and complexity across different energy systems. This Ph.D. project aims to address these challenges by developing scalable, data-driven approaches for monitoring and prognostics. By focusing on creating adaptable and generic frameworks, the research seeks to provide robust solutions for real-world monitoring and prognostic problems for energy assets.

Accurate estimation of the state-of-charge (SOC) in lithium-ion batteries (LIBs) is paramount for the safe operation of battery management systems. Despite the effectiveness of existing SOC estimation methods, their generalization across different battery chemistries and operating conditions remains challenging. Current data-driven approaches necessitate extensive data collection for each battery chemistry and operating condition, leading to a costly and time-consuming process. Hence, there is a critical need to enhance the generalization and adaptability of SOC estimators. In this paper, we propose a novel SOC estimation method based on Regression-based Unsupervised Domain Adaptation. We evaluate the performance of this method in cross-battery and cross-temperature SOC estimation scenarios. Additionally, we conduct a comparative analysis with a widely-used classification-based unsupervised domain adaptation approach. Our findings demonstrate the superiority of the regression-based unsupervised domain adaptation method in achieving accurate SOC estimation for batteries.